Abstract
Current data description learning methods for novelty detection such as support vector data description and small sphere with large margin construct a spherically shaped boundary around a normal data set to separate this set from abnormal data. The volume of this sphere is minimized to reduce the chance of accepting abnormal data. However those learning methods do not guarantee that the single spherically shaped boundary can best describe the normal data set if there exist some distinctive data distributions in this set. We propose in this paper a new data description learning method that constructs a set of spherically shaped boundaries to provide a better data description to the normal data set. An optimisation problem is proposed and solving this problem results in an iterative learning algorithm to determine the set of spherically shaped boundaries. We prove that the classification error will be reduced after each iteration in our learning method. Experimental results on 28 well-known data sets show that the proposed method provides lower classification error rates.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bishop, C.M.: Novelty detection and neural network validation. In: IEEE Proceedings of Vision, Image and Signal Processing, pp. 217–222 (1994)
Barnett, V., Lewis, T.: Outliers in statistical data, 3rd edn. Wiley, Chichester (1978)
Campbell, C., Bennet, K.P.: A linear programming approach to novelty detection. Advances in Neural Information Processing Systems 14 (2001)
Chang, C.-C., Lin, C.-J.: LIBSVM: A Library for Support Vector Machines, http://www.csie.ntu.edu.tw/~cjlinlibsvm
Hao, P.Y., Liu, Y.H.: A New Multi-class Support Vector Machine with Multi-sphere in the Feature Space. In: Okuno, H.G., Ali, M. (eds.) IEA/AIE 2007. LNCS (LNAI), vol. 4570, pp. 756–765. Springer, Heidelberg (2007)
Kubat, M., Matwin, S.: Addressing the curse of imbalanced training set: One-sided selection. In: Proc. 14th International Conference on Machine Learning, pp. 179–186 (1997)
Le, T., Tran, D., Ma, W., Sharma, D.: An Optimal Sphere and Two Large Margins Approach for Novelty Detection. In: Proc. IEEE World Congress on Computational Intelligence, WCCI (accepted 2010)
Lin, Y., Lee, Y., Wahba, G.: Support vector machine for classification in nonstandard situations. Machine Learning 15, 1115–1148 (2002)
Moya, M.M., Koch, M.W., Hostetler, L.D.: One-class classifier networks for target recognition applications. In: Proceedings of World Congress on Neural Networks, pp. 797–801 (1991)
Mu, T., Nandi, A.K.: Multiclass Classification Based on Extended Support Vector Data Description. IEEE Transactions on Systems, Man and Cybernetics Part B: Cybernetics 39(5), 1206–1217 (2009)
Parra, L., Deco, G., Miesbach, S.: Statistical independence and novelty detection with information preserving nonlinear maps. Neural Computation 8, 260–269 (1996)
Roberts, S., Tarassenko, L.: A Probabilistic Resource Allocation Network for Novelty Detection. Neural Computation 6, 270–284 (1994)
Schlkopf, Smola, A.J.: Learning with kernels. The MIT Press, Cambridge (2002)
Tax, D.M.J., Duin, R.P.W.: Support vector data description. Machine Learning 54, 45–56 (2004)
Tax, D.M.J.: Datasets (2009), http://ict.ewi.tudelft.nl/~davidt/occ/index.html
Towel, G.G.: Local expert autoassociator for anomaly detection. In: Proc. 17th International Conference on Machine Learning, pp. 1023–1030. Morgan Kaufmann Publishers Inc., San Francisco (2000)
Vapnik, V.: The nature of statistical learning theory. Springer, Heidelberg (1995)
Vert, J., Vert, J.P.: Consistency and convergence rates of one class svm and related algorithm. Journal of Machine Learning Research 7, 817–854 (2006)
Xiao, Y., Liu, B., Cao, L., Wu, X., Zhang, C., Hao, Z., Yang, F., Cao, J.: Multi-sphere Support Vector Data Description for Outliers Detection on Multi-Distribution Data. In: Proc. IEEE International Conference on Data Mining Workshops, pp. 82–88 (2009)
Yu, M., Ye, J.: A Small Sphere and Large Margin Approach for Novelty Detection Using Training Data with Outliers. IEEE Transaction on Pattern Analysis and Machine Intelligence 31, 2088–2092 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Le, T., Tran, D., Ma, W., Sharma, D. (2011). Multiple Distribution Data Description Learning Algorithm for Novelty Detection. In: Huang, J.Z., Cao, L., Srivastava, J. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2011. Lecture Notes in Computer Science(), vol 6635. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20847-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-20847-8_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20846-1
Online ISBN: 978-3-642-20847-8
eBook Packages: Computer ScienceComputer Science (R0)